Python爬虫之-前程无忧招聘网站（可运行源码）

 

今天爬了前程无忧，分享下代码~

可以直接运行的，也很简单，就不做注释了。

原创：禁止转载

2019-09-05更新---------------------------

  今天有人关注了这个代码 之前的代码都是刚开始学习的时候写的，自己都有点看不下去哈哈，现在贴一个简单些的代码，大家一起进步哈哈~

#coding:utf-8
import json
import time
import urllib
import urllib2
import re
from bs4 import BeautifulSoup

#__author__='小菜菜1223'


def run(num,typ):
    url = 'https://search.51job.com/list/120300,000000,0000,00,9,99,' + str(typ) + ',2,' + str(num) + '.html?lang=c&stype=1&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare='
    a = urllib2.urlopen(url)
    html = a.read()
    soup = BeautifulSoup(html,'lxml')
    main(soup)

def main(soup):
    #获取公司名称
    account_unitnames = soup.find_all(attrs={'class':'t2'})
    for n, v in enumerate(account_unitnames):
        if n == 0:continue
        print n,v.a['title']
    #获取地点
    positions = soup.find_all(attrs={'class':'t3'})
    for n, v in enumerate(positions):
        print n,v.contents
    #获取薪资
    money = soup.find_all(attrs={'class':'t4'})
    for n, v in enumerate(money):
        print n,v.contents
    #获取日期
    date = soup.find_all(attrs={'class':'t5'})
    for n, v in enumerate(date):
        print n,v.contents

if __name__ == '__main__':
    #第一个参数是职位 第二个参数是页数
    run('java',0)